A Review on How Human Aging Influences Facial Expression Recognition (FER)

Abstract

An active research topic in computer vision for a while has been Facial Expression Recognition (FER), but study on how human aging affects computational FER, is only slowly budding. A review has been conducted on this study based on two collected databases from the psychology society-the Lifespan and FACES, and it was found that human aging has significant impact on computational FER. The reasons were also analyzed, based on which two schemes have been proposed-the age group constrained and aging details removal. The success of these schemes for Lifespan FER has been evaluated, and high accuracies were obtained on both databases. A solution has been proposed for facial aging during growing years, which would account for the gradual change in feature dimensions of the face. This could be implemented in the future perhaps.

Hearing, Emotion, Amplification, Research, and Training Workshop: Current Understanding of Hearing Loss and Emotion Perception and Priorities for Future Research

“…There are many commercially based systems available on the market. Of relevance to audiology, there is evidence to suggest that aging may have a significant impact on automated facial emotion recognition (Mary & Jayakumar, 2016), but the understanding of the extent to which aging influences automated emotion recognition is still in its infancy.…”